© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38314
    Prev
    Next
    INDEX
    Explanations

    military fleets and collections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĶ¿åĬ¡
    -0.10
    pled
    -0.10
    å¼Ģæľº
    -0.08
    æĹ¶æ®µ
    -0.08
    ective
    -0.08
    飵
    -0.08
    å¢ĥå¤ĸ
    -0.08
    iken
    -0.08
    egis
    -0.08
    人寿
    -0.08
    POSITIVE LOGITS
     collection
    0.13
    collection
    0.12
    åºŀ大
    0.12
     fleets
    0.11
    éĺµå®¹
    0.11
    é¾
    0.10
    å¹²éĥ¨éĺŁä¼į
    0.10
    åºŀ大çļĦ
    0.10
     inventory
    0.10
     fleet
    0.10
    Activations Density 0.133%

    No Known Activations